Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3246 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4840. Min Act: -0.0003

Data Index: 166159 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5479. Min Act: -0.0003

Data Index: 1023560 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4903. Min Act: -0.0003

Data Index: 799762 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5075. Min Act: -0.0003

Data Index: 281243 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5228. Min Act: -0.0003

Data Index: 723377 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4819. Min Act: -0.0003

Data Index: 532747 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4997. Min Act: -0.0003

Data Index: 487191 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4808. Min Act: -0.0003

Data Index: 1259487 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4915. Min Act: -0.0003

Data Index: 917190 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5256. Min Act: -0.0003

Data Index: 713124 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4607. Min Act: -0.0003

Data Index: 510558 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5244. Min Act: -0.0003

Data Index: 1050008 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4405. Min Act: -0.0003

Data Index: 289792 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5054. Min Act: -0.0003

Data Index: 311924 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4882. Min Act: -0.0003

Data Index: 877959 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4883. Min Act: -0.0003

Data Index: 146049 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5041. Min Act: -0.0003

Data Index: 1264917 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4854. Min Act: -0.0003

Data Index: 738427 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.5018. Min Act: -0.0003

Data Index: 238692 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.5479. Min Range: -0.5479

Max Act: 0.4832. Min Act: -0.0003

Data Index: 166232 (C4 (Web Text))

Max Activating Token Index: 388